| .. |
|
moeLoadBalancer
|
feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226)
|
2025-06-25 22:25:13 -07:00 |
|
utils
|
refactor: unique_ptr instead of shared_ptr (#4697)
|
2025-05-29 22:49:35 +02:00 |
|
bufferManager.cpp
|
|
|
|
bufferView.h
|
|
|
|
CMakeLists.txt
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
cudaMemPool.cpp
|
|
|
|
cudaMemPool.h
|
|
|
|
decoderState.cpp
|
refactor: decoding inputs (#5679)
|
2025-07-06 08:21:02 +02:00 |
|
decodingLayerWorkspace.cpp
|
|
|
|
decodingLayerWorkspace.h
|
|
|
|
decodingOutput.cpp
|
|
|
|
eagleBuffers.cpp
|
fix: Eagle decoding in TRT flow (#4229)
|
2025-05-14 16:10:49 +02:00 |
|
explicitDraftTokensBuffers.cpp
|
|
|
|
explicitDraftTokensModule.h
|
|
|
|
gptDecoder.cpp
|
refactor: Clean up DecodingInput and DecodingOutput (#5617)
|
2025-07-01 14:31:42 +02:00 |
|
gptDecoderBatched.cpp
|
refactor: decoding inputs (#5679)
|
2025-07-06 08:21:02 +02:00 |
|
gptJsonConfig.cpp
|
Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338)
|
2025-04-08 23:51:27 +08:00 |
|
iBuffer.cpp
|
|
|
|
ipcNvlsMemory.cu
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
ipcSocket.cpp
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
ipcSocket.h
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
ipcUtils.cpp
|
Cherry pick feat/llama4 to main (#4739)
|
2025-05-30 05:28:40 +08:00 |
|
iTensor.cpp
|
|
|
|
jsonSerialization.h
|
|
|
|
layerProfiler.cpp
|
|
|
|
layerProfiler.h
|
|
|
|
lookaheadBuffers.cpp
|
Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338)
|
2025-04-08 23:51:27 +08:00 |
|
loraCache.cpp
|
fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow. (#4399)
|
2025-05-19 14:25:36 -07:00 |
|
loraManager.cpp
|
fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow. (#4399)
|
2025-05-19 14:25:36 -07:00 |
|
loraManager.h
|
|
|
|
loraModule.cpp
|
|
|
|
loraUtils.cpp
|
|
|
|
loraUtils.h
|
|
|
|
mcastDeviceMemory.cpp
|
[TRTLLM-4647][fix] Fix the no fusion allreduce hanging (#4594)
|
2025-06-04 18:26:13 -07:00 |
|
mcastDeviceMemory.h
|
Adding two-shot allreduce kernel and mnnvl multicasting buffer (#4216)
|
2025-05-22 03:42:36 +08:00 |
|
mcastGPUBuffer.h
|
Adding two-shot allreduce kernel and mnnvl multicasting buffer (#4216)
|
2025-05-22 03:42:36 +08:00 |
|
memoryCounters.cpp
|
|
|
|
ncclCommunicator.cpp
|
|
|
|
ncclCommunicator.h
|
|
|
|
promptTuningParams.cpp
|
Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)
|
2025-05-12 22:32:29 +02:00 |
|
runtimeKernels.cu
|
[TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092)
|
2025-05-14 23:10:04 +02:00 |
|
runtimeKernels.h
|
chore: Clean up cpp runtime (#4449)
|
2025-05-28 16:32:59 +02:00 |
|
tensorView.h
|
|
|
|
tllmBuffers.cpp
|
|
|
|
tllmBuffers.h
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
tllmLogger.cpp
|
|
|
|
tllmRuntime.cpp
|
Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)
|
2025-05-12 22:32:29 +02:00 |
|
tllmRuntime.h
|
Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)
|
2025-05-12 22:32:29 +02:00 |
|
tllmStreamReaders.cpp
|
feat: Integrate GPUDirect Storage (GDS) into Executor API (#3582)
|
2025-04-18 15:59:21 +08:00 |
|
tllmStreamReaders.h
|
feat: Integrate GPUDirect Storage (GDS) into Executor API (#3582)
|
2025-04-18 15:59:21 +08:00 |
|
torch.h
|
|
|
|
torchUtils.h
|
[TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123)
|
2025-05-14 15:48:07 +08:00 |
|
torchView.h
|
|
|
|
workerPool.cpp
|
|
|
|
workerPool.h
|
|
|
|
worldConfig.cpp
|
bug: Fix hang bug when context server doesn't have enough capacity for KV Cache (#3095)
|
2025-04-21 15:16:55 +08:00 |
